Welcome to the September 2020 SIGCHI edition of ACM TechNews.

ACM TechNews - SIGCHI Edition is a sponsored special edition of the ACM TechNews news-briefing service focused on issues in Human Computer Interaction (HCI). This service serves as a resource for ACM-SIGCHI Members to keep abreast of the latest news in areas related to HCI and is distributed to all ACM SIGCHI members the first Tuesday of every month. ACM TechNews is a benefit of ACM membership and is distributed three times per week on Mondays, Wednesday, and Fridays to over 100,000 ACM members from over 100 countries around the world. ACM TechNews provides timely coverage of established and emerging areas of computer science, the latest trends in information technology, and related science, society, and technology news. For more information on ACM TechNews and joining the ACM, please click. The Interactions mobile app is available for free on iOS, Android, and Kindle platforms. Download it today and flip through the full-color magazine pages on your tablet or view it in a simplified low-bandwidth text mode on your phone. And be sure to check out the Interactions website, where you can access current and past articles and read the latest entries in our ever-expanding collection of blogs.

Exoskeleton Research Marches Forward with NIST Study on Fit
NIST News
August 20, 2020

Researchers at the U.S. National Institute of Standards and Technology (NIST) developed an optical tracking system (OTS) to test whether an exoskeleton and its wearer fit well together. The OTS employs cameras that emit light and record its reflection from spherical markers positioned on objects of interest; a computer then calculates the three-dimensional (3D) position of the labeled objects. This method tracks the movement of an exoskeleton and test pieces, or artifacts, fastened to its user. The researchers assembled two artificial legs as testbeds: one with an off-the-shelf prosthetic knee, and the other with a three-dimensional (3D)-printed knee. OTS tests found the wearer's leg and the exoskeleton largely moved in harmony, with brief moments of misalignment.

Full Article

USC Viterbi Researchers Win 1st Place, Develop Covid-19 Risk Score for Los Angeles
USC Viterbi School of Engineering
Lila Jones
August 26, 2020

Researchers at the University of Southern California (USC) Viterbi School of Engineering were named first-place winners of the 2020 Covid-19 Computational Challenge, for their development of a metric to evaluate the risk of exposure to the virus. Their metric generates a “risk score” for a community representing the number of individuals per 10,000 estimated to become infected in the next 24 hours. USC Viterbi's Bhaskar Krishnamacharya said, "This work will be broadly beneficial to citizens in communities worldwide by making it easier and more intuitive and tangible to understand and track their own individual level of risk when going about their activities in the community."

Full Article

A Blind Musician Can Feel a Conductor's Movements, Thanks to a High-Tech Baton
CNN
Stephanie Bailey
August 20, 2020

The founders of Human Instruments, an organization that collaborates with people with physical disabilities to design musical technologies, have developed the "Haptic Baton" to allow a blind musician to play with an orchestra. Used like a standard baton, the Haptic Baton features sensors that detect the direction and acceleration of the conductor’s movements, which are turned into vibrations that are transmitted wirelessly to receivers worn by the musician on a wrist or ankle on each side of his or her body. Kyungho Jeon, a virtuoso percussionist based in Seoul, South Korea, who was born blind, worked with Human Instruments to develop the Haptic Baton, which he now can use to achieve his dream of playing with an ensemble. Said Jeon, "Through the vibration that is delivered by the device, I can feel how the conductor beats: strong, soft, smooth or long."

Full Article

Eye-Tracking Mask Could Monitor People's Reactions to What They See
New Scientist
Layal Liverpool
August 20, 2020

University of Massachusetts Amherst (UMass Amherst) researchers have developed an eye-tracking mask that could monitor people's reactions to visual input. The team designed two fabric-based washable, reusable electrodes, which facilitate continuous tracking of the wearer's eye movements and pulse for up to eight hours. The Chesma mask is being used for overnight sleep studies, and potential applications also include human-computer interaction. UMass Amherst's Trisha Andrew said, "If you are staring at a screen while wearing the mask, [it] can tell which quadrant of the screen your eyes are drawn to or are focusing on. Coupled with pulse, that provides insight into awareness and emotional state."

Full Article

Researchers' AI Can Perform 3D Motion Capture With Any Off-the-Shelf Camera
Venture Beat
Kyle Wiggers
August 25, 2020

While motion capture typically requires special equipment, cameras, and software, researchers at the Max Planck Institute in Germany and Facebook Reality Labs have developed a machine learning algorithm that enables motion capture using any off-the-shelf DSLR camera running at 25 frames per second. The PhysCap algorithm uses a convolutional neural network (CNN) to estimate body poses in three dimensions, and a second CNN to predict foot contact and motion states for every frame; it then produces kinematic pose estimates as closely as possible to account for gravity, collisions, foot placement, and other factors. Said the researchers, "Since the output of PhysCap is environment-aware and the returned root position is global, it is directly suitable for virtual character animation, without any further post-processing."

Full Article

Smartwatch Tracks Medication Levels to Personalize Treatments
UCLA Samueli Newsroom
August 6, 2020

Researchers at the University of California, Los Angeles Samueli School of Engineering and the Stanford University School of Medicine have created a custom smartwatch that allows for the real-time tracking of drug levels in the body. The wearable device could facilitate a more personalized approach to medicine in which ideal drugs and dosages are tailored to the individual. Rather than rely on repeated blood draws at the hospital, the device uses a sensor that analyzes the chemicals that appear in one’s sweat, permitting continuous, non-invasive tracking. According to the researchers, the smartwatch can accurately detect a drug's unique electrochemical signal amid signals from other molecules circulating in the body in higher concentrations.

Full Article

Hospitality Industry Turns to Tech to Lure Guests Back
The Wall Street Journal
Sara Castellanos
August 5, 2020

The U.S. hospitality sector is heavily investing in automation and digital technologies to win back guests amid the coronavirus pandemic. The California-based Viceroy Hotel Group is deploying voice-activated digital assistants such as Amazon's Alexa to reduce physical touchpoints, enabling guests to control lights and TVs in their rooms hands-free. The devices also are integrated with systems like Viceroy's cloud-based property management system, to allow guests to remotely request extra towels or late checkouts. Meanwhile, customers at MGM Resorts International hotels can use a mobile phone application to process payment, verify their identity, and obtain digital room keys. RLH Corp. is developing software in-house to automate invoice generation, and using artificial intelligence-based software from cloud communications firm BluIP to answer guest queries via phone.

Full Article

NTU Singapore Scientists Develop AI System for Precision Recognition of Hand Gestures
Nanyang Technological University (Singapore)
August 13, 2020

Researchers at Nanyang Technological University (NTU) in Singapore have created an artificial intelligence (AI) system that recognizes hand gestures more accurately than existing methods. Their "bioinspired" data fusion system uses stretchable strain sensors made from single-walled carbon nanotubes, which adhere to the skin but which, the researchers say, cannot be seen in camera images. The system, which combines a convolutional neural network, a multilayer neural network, and a sparse neural network, was able to guide a robot controlled by hand gestures through a maze with zero errors. Said NTU's Wang Ming, "The secret behind the high accuracy in our architecture lies in the fact that the visual and somatosensory information can interact and complement each other at an early stage before carrying out complex interpretation."

Full Article

MIT Develops Open Source Tool to Support Spontaneous Online Conversations
Campus Technology
Rhea Kelly
August 5, 2020

Researchers at Massachusetts Institute of Technology's (MIT) Sloan School of Management have developed an open source software platform that enables private, on-the-spot conversations online. They said the Minglr platform aims to replicate office-like interactions in a virtual environment to "boost the desirability and feasibility of remote work, learning, and professional networking." The platform is built on the open source videoconferencing system Jitsi, enabling users to see a list of people available to talk, choose who they want to chat with, accept or deny chat requests, and hold impromptu conversations in private video rooms. Said MIT's Jaeyoon Song, "With Minglr, we see a future that involves much richer and deeper online interaction."

Full Article

Why People Get Sick in VR
UNSW Sydney Newsroom (Australia)
Sherry Landow
August 20, 2020

Researchers at the University of New South Wales (UNSW) Sydney in Australia found a potential explanation for why virtual reality (VR) technology makes certain people experience "cybersickness" (similar to motion sickness) in “scene instability,” the amount a virtual environment rotates in relation to one’s head’s actual rotation. The researchers had test subjects wear a head-mounted display (HMD) and move around a virtual space. They found that the angular difference between one’s virtual and physical head (Difference in Virtual to Physical, or DVP) creates the illusion of an unstable environment, and could be used to gauge the severity and likelihood of cybersickness. Said UNSW's Juno Kim, "The scene instability theory is the first to generate a testable hypothesis for understanding cybersickness and its causes.”

Full Article